Training in progress, epoch 0
Browse files- all_results.json +11 -11
- eval_results.json +6 -6
- pytorch_model.bin +1 -1
- runs/Apr25_10-19-53_96b30dde7809/events.out.tfevents.1682419148.96b30dde7809.539.2 +3 -0
- runs/Apr25_10-54-20_96b30dde7809/1682420063.7734914/events.out.tfevents.1682420063.96b30dde7809.539.4 +3 -0
- runs/Apr25_10-54-20_96b30dde7809/events.out.tfevents.1682420063.96b30dde7809.539.3 +3 -0
- train_results.json +6 -6
- trainer_state.json +406 -85
- training_args.bin +1 -1
all_results.json
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second":
|
| 8 |
-
"total_flos":
|
| 9 |
-
"train_loss": 0.
|
| 10 |
-
"train_runtime":
|
| 11 |
-
"train_samples_per_second":
|
| 12 |
-
"train_steps_per_second": 0.
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 9.91,
|
| 3 |
+
"eval_accuracy": 0.9895561357702349,
|
| 4 |
+
"eval_loss": 0.029892772436141968,
|
| 5 |
+
"eval_runtime": 5.5444,
|
| 6 |
+
"eval_samples_per_second": 69.078,
|
| 7 |
+
"eval_steps_per_second": 8.657,
|
| 8 |
+
"total_flos": 8.479620642524774e+17,
|
| 9 |
+
"train_loss": 0.11231542806156346,
|
| 10 |
+
"train_runtime": 1101.7928,
|
| 11 |
+
"train_samples_per_second": 31.249,
|
| 12 |
+
"train_steps_per_second": 0.554
|
| 13 |
}
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 9.91,
|
| 3 |
+
"eval_accuracy": 0.9895561357702349,
|
| 4 |
+
"eval_loss": 0.029892772436141968,
|
| 5 |
+
"eval_runtime": 5.5444,
|
| 6 |
+
"eval_samples_per_second": 69.078,
|
| 7 |
+
"eval_steps_per_second": 8.657
|
| 8 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 110394865
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5213cb93a6c5475791b409e7e3272749aec8ac024b4bb76ccc80b3c891744f31
|
| 3 |
size 110394865
|
runs/Apr25_10-19-53_96b30dde7809/events.out.tfevents.1682419148.96b30dde7809.539.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:053289338d9b24cba661a88db3c7c20e6c3f9f733a316925f3f5afdeb4d1e599
|
| 3 |
+
size 411
|
runs/Apr25_10-54-20_96b30dde7809/1682420063.7734914/events.out.tfevents.1682420063.96b30dde7809.539.4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:facc21995f72cc4af228216c8972a8658bd9530d9ad85799da55ccb333e42508
|
| 3 |
+
size 5952
|
runs/Apr25_10-54-20_96b30dde7809/events.out.tfevents.1682420063.96b30dde7809.539.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:655aa6b7dff0a38c2970b3b8ea742054dbd7ad48c90ea8ffd90a3a8990954ab8
|
| 3 |
+
size 5993
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 9.91,
|
| 3 |
+
"total_flos": 8.479620642524774e+17,
|
| 4 |
+
"train_loss": 0.11231542806156346,
|
| 5 |
+
"train_runtime": 1101.7928,
|
| 6 |
+
"train_samples_per_second": 31.249,
|
| 7 |
+
"train_steps_per_second": 0.554
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,160 +1,481 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "swin-tiny-patch4-window7-224-mixed-bottoms/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 0.16,
|
| 12 |
-
"learning_rate": 4.
|
| 13 |
-
"loss": 0.
|
| 14 |
"step": 10
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.32,
|
| 18 |
-
"learning_rate": 4.
|
| 19 |
-
"loss": 0.
|
| 20 |
"step": 20
|
| 21 |
},
|
| 22 |
{
|
| 23 |
-
"epoch": 0.
|
| 24 |
-
"learning_rate": 4.
|
| 25 |
-
"loss": 0.
|
| 26 |
"step": 30
|
| 27 |
},
|
| 28 |
{
|
| 29 |
-
"epoch": 0.
|
| 30 |
-
"learning_rate":
|
| 31 |
-
"loss": 0.
|
| 32 |
"step": 40
|
| 33 |
},
|
| 34 |
{
|
| 35 |
-
"epoch": 0.
|
| 36 |
-
"learning_rate":
|
| 37 |
-
"loss": 0.
|
| 38 |
"step": 50
|
| 39 |
},
|
| 40 |
{
|
| 41 |
-
"epoch": 0.
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss": 0.
|
| 44 |
"step": 60
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch":
|
| 48 |
-
"eval_accuracy": 0.
|
| 49 |
-
"eval_loss": 0.
|
| 50 |
-
"eval_runtime":
|
| 51 |
-
"eval_samples_per_second":
|
| 52 |
-
"eval_steps_per_second":
|
| 53 |
-
"step":
|
| 54 |
},
|
| 55 |
{
|
| 56 |
-
"epoch": 1.
|
| 57 |
-
"learning_rate":
|
| 58 |
-
"loss": 0.
|
| 59 |
"step": 70
|
| 60 |
},
|
| 61 |
{
|
| 62 |
-
"epoch": 1.
|
| 63 |
-
"learning_rate":
|
| 64 |
-
"loss": 0.
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
-
"epoch": 1.
|
| 69 |
-
"learning_rate":
|
| 70 |
-
"loss": 0.
|
| 71 |
"step": 90
|
| 72 |
},
|
| 73 |
{
|
| 74 |
-
"epoch": 1.
|
| 75 |
-
"learning_rate":
|
| 76 |
-
"loss": 0.
|
| 77 |
"step": 100
|
| 78 |
},
|
| 79 |
{
|
| 80 |
-
"epoch": 1.
|
| 81 |
-
"learning_rate":
|
| 82 |
-
"loss": 0.
|
| 83 |
"step": 110
|
| 84 |
},
|
| 85 |
{
|
| 86 |
-
"epoch": 1.
|
| 87 |
-
"learning_rate":
|
| 88 |
-
"loss": 0.
|
| 89 |
"step": 120
|
| 90 |
},
|
| 91 |
{
|
| 92 |
"epoch": 2.0,
|
| 93 |
-
"eval_accuracy": 0.
|
| 94 |
-
"eval_loss": 0.
|
| 95 |
-
"eval_runtime": 5.
|
| 96 |
-
"eval_samples_per_second":
|
| 97 |
-
"eval_steps_per_second": 9.
|
| 98 |
-
"step":
|
| 99 |
},
|
| 100 |
{
|
| 101 |
-
"epoch": 2.
|
| 102 |
-
"learning_rate":
|
| 103 |
-
"loss": 0.
|
| 104 |
"step": 130
|
| 105 |
},
|
| 106 |
{
|
| 107 |
-
"epoch": 2.
|
| 108 |
-
"learning_rate":
|
| 109 |
-
"loss": 0.
|
| 110 |
"step": 140
|
| 111 |
},
|
| 112 |
{
|
| 113 |
-
"epoch": 2.
|
| 114 |
-
"learning_rate":
|
| 115 |
-
"loss": 0.
|
| 116 |
"step": 150
|
| 117 |
},
|
| 118 |
{
|
| 119 |
-
"epoch": 2.
|
| 120 |
-
"learning_rate":
|
| 121 |
-
"loss": 0.
|
| 122 |
"step": 160
|
| 123 |
},
|
| 124 |
{
|
| 125 |
-
"epoch": 2.
|
| 126 |
-
"learning_rate":
|
| 127 |
-
"loss": 0.
|
| 128 |
"step": 170
|
| 129 |
},
|
| 130 |
{
|
| 131 |
-
"epoch": 2.
|
| 132 |
-
"learning_rate":
|
| 133 |
-
"loss": 0.
|
| 134 |
"step": 180
|
| 135 |
},
|
| 136 |
{
|
| 137 |
"epoch": 2.99,
|
| 138 |
-
"eval_accuracy": 0.
|
| 139 |
-
"eval_loss": 0.
|
| 140 |
-
"eval_runtime":
|
| 141 |
-
"eval_samples_per_second":
|
| 142 |
-
"eval_steps_per_second":
|
| 143 |
-
"step":
|
| 144 |
},
|
| 145 |
{
|
| 146 |
-
"epoch":
|
| 147 |
-
"
|
| 148 |
-
"
|
| 149 |
-
"
|
| 150 |
-
|
| 151 |
-
|
| 152 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 153 |
}
|
| 154 |
],
|
| 155 |
-
"max_steps":
|
| 156 |
-
"num_train_epochs":
|
| 157 |
-
"total_flos":
|
| 158 |
"trial_name": null,
|
| 159 |
"trial_params": null
|
| 160 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.9895561357702349,
|
| 3 |
+
"best_model_checkpoint": "swin-tiny-patch4-window7-224-mixed-bottoms/checkpoint-610",
|
| 4 |
+
"epoch": 9.907192575406032,
|
| 5 |
+
"global_step": 610,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 0.16,
|
| 12 |
+
"learning_rate": 4.975124378109453e-05,
|
| 13 |
+
"loss": 0.5548,
|
| 14 |
"step": 10
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.32,
|
| 18 |
+
"learning_rate": 4.8922056384742954e-05,
|
| 19 |
+
"loss": 0.3681,
|
| 20 |
"step": 20
|
| 21 |
},
|
| 22 |
{
|
| 23 |
+
"epoch": 0.49,
|
| 24 |
+
"learning_rate": 4.8092868988391376e-05,
|
| 25 |
+
"loss": 0.3048,
|
| 26 |
"step": 30
|
| 27 |
},
|
| 28 |
{
|
| 29 |
+
"epoch": 0.65,
|
| 30 |
+
"learning_rate": 4.7263681592039805e-05,
|
| 31 |
+
"loss": 0.2445,
|
| 32 |
"step": 40
|
| 33 |
},
|
| 34 |
{
|
| 35 |
+
"epoch": 0.81,
|
| 36 |
+
"learning_rate": 4.643449419568823e-05,
|
| 37 |
+
"loss": 0.209,
|
| 38 |
"step": 50
|
| 39 |
},
|
| 40 |
{
|
| 41 |
+
"epoch": 0.97,
|
| 42 |
+
"learning_rate": 4.560530679933665e-05,
|
| 43 |
+
"loss": 0.1816,
|
| 44 |
"step": 60
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 0.99,
|
| 48 |
+
"eval_accuracy": 0.9451697127937336,
|
| 49 |
+
"eval_loss": 0.12642310559749603,
|
| 50 |
+
"eval_runtime": 24.4251,
|
| 51 |
+
"eval_samples_per_second": 15.681,
|
| 52 |
+
"eval_steps_per_second": 1.965,
|
| 53 |
+
"step": 61
|
| 54 |
},
|
| 55 |
{
|
| 56 |
+
"epoch": 1.14,
|
| 57 |
+
"learning_rate": 4.477611940298508e-05,
|
| 58 |
+
"loss": 0.1838,
|
| 59 |
"step": 70
|
| 60 |
},
|
| 61 |
{
|
| 62 |
+
"epoch": 1.3,
|
| 63 |
+
"learning_rate": 4.39469320066335e-05,
|
| 64 |
+
"loss": 0.1684,
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
+
"epoch": 1.46,
|
| 69 |
+
"learning_rate": 4.311774461028192e-05,
|
| 70 |
+
"loss": 0.2074,
|
| 71 |
"step": 90
|
| 72 |
},
|
| 73 |
{
|
| 74 |
+
"epoch": 1.62,
|
| 75 |
+
"learning_rate": 4.228855721393035e-05,
|
| 76 |
+
"loss": 0.144,
|
| 77 |
"step": 100
|
| 78 |
},
|
| 79 |
{
|
| 80 |
+
"epoch": 1.79,
|
| 81 |
+
"learning_rate": 4.145936981757877e-05,
|
| 82 |
+
"loss": 0.1467,
|
| 83 |
"step": 110
|
| 84 |
},
|
| 85 |
{
|
| 86 |
+
"epoch": 1.95,
|
| 87 |
+
"learning_rate": 4.0630182421227194e-05,
|
| 88 |
+
"loss": 0.1673,
|
| 89 |
"step": 120
|
| 90 |
},
|
| 91 |
{
|
| 92 |
"epoch": 2.0,
|
| 93 |
+
"eval_accuracy": 0.9399477806788512,
|
| 94 |
+
"eval_loss": 0.14775583148002625,
|
| 95 |
+
"eval_runtime": 5.0443,
|
| 96 |
+
"eval_samples_per_second": 75.928,
|
| 97 |
+
"eval_steps_per_second": 9.516,
|
| 98 |
+
"step": 123
|
| 99 |
},
|
| 100 |
{
|
| 101 |
+
"epoch": 2.11,
|
| 102 |
+
"learning_rate": 3.980099502487562e-05,
|
| 103 |
+
"loss": 0.1147,
|
| 104 |
"step": 130
|
| 105 |
},
|
| 106 |
{
|
| 107 |
+
"epoch": 2.27,
|
| 108 |
+
"learning_rate": 3.8971807628524045e-05,
|
| 109 |
+
"loss": 0.1403,
|
| 110 |
"step": 140
|
| 111 |
},
|
| 112 |
{
|
| 113 |
+
"epoch": 2.44,
|
| 114 |
+
"learning_rate": 3.8142620232172474e-05,
|
| 115 |
+
"loss": 0.152,
|
| 116 |
"step": 150
|
| 117 |
},
|
| 118 |
{
|
| 119 |
+
"epoch": 2.6,
|
| 120 |
+
"learning_rate": 3.73134328358209e-05,
|
| 121 |
+
"loss": 0.1594,
|
| 122 |
"step": 160
|
| 123 |
},
|
| 124 |
{
|
| 125 |
+
"epoch": 2.76,
|
| 126 |
+
"learning_rate": 3.6484245439469325e-05,
|
| 127 |
+
"loss": 0.1423,
|
| 128 |
"step": 170
|
| 129 |
},
|
| 130 |
{
|
| 131 |
+
"epoch": 2.92,
|
| 132 |
+
"learning_rate": 3.565505804311775e-05,
|
| 133 |
+
"loss": 0.125,
|
| 134 |
"step": 180
|
| 135 |
},
|
| 136 |
{
|
| 137 |
"epoch": 2.99,
|
| 138 |
+
"eval_accuracy": 0.9738903394255874,
|
| 139 |
+
"eval_loss": 0.06674866378307343,
|
| 140 |
+
"eval_runtime": 4.4641,
|
| 141 |
+
"eval_samples_per_second": 85.796,
|
| 142 |
+
"eval_steps_per_second": 10.752,
|
| 143 |
+
"step": 184
|
| 144 |
},
|
| 145 |
{
|
| 146 |
+
"epoch": 3.09,
|
| 147 |
+
"learning_rate": 3.4825870646766175e-05,
|
| 148 |
+
"loss": 0.1046,
|
| 149 |
+
"step": 190
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 3.25,
|
| 153 |
+
"learning_rate": 3.39966832504146e-05,
|
| 154 |
+
"loss": 0.124,
|
| 155 |
+
"step": 200
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 3.41,
|
| 159 |
+
"learning_rate": 3.316749585406302e-05,
|
| 160 |
+
"loss": 0.093,
|
| 161 |
+
"step": 210
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 3.57,
|
| 165 |
+
"learning_rate": 3.233830845771145e-05,
|
| 166 |
+
"loss": 0.1084,
|
| 167 |
+
"step": 220
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 3.74,
|
| 171 |
+
"learning_rate": 3.150912106135987e-05,
|
| 172 |
+
"loss": 0.1076,
|
| 173 |
+
"step": 230
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 3.9,
|
| 177 |
+
"learning_rate": 3.067993366500829e-05,
|
| 178 |
+
"loss": 0.1034,
|
| 179 |
+
"step": 240
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 4.0,
|
| 183 |
+
"eval_accuracy": 0.9817232375979112,
|
| 184 |
+
"eval_loss": 0.05531755089759827,
|
| 185 |
+
"eval_runtime": 4.4942,
|
| 186 |
+
"eval_samples_per_second": 85.221,
|
| 187 |
+
"eval_steps_per_second": 10.68,
|
| 188 |
+
"step": 246
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 4.06,
|
| 192 |
+
"learning_rate": 2.9850746268656714e-05,
|
| 193 |
+
"loss": 0.1161,
|
| 194 |
+
"step": 250
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 4.22,
|
| 198 |
+
"learning_rate": 2.9021558872305143e-05,
|
| 199 |
+
"loss": 0.0833,
|
| 200 |
+
"step": 260
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 4.39,
|
| 204 |
+
"learning_rate": 2.8192371475953565e-05,
|
| 205 |
+
"loss": 0.0546,
|
| 206 |
+
"step": 270
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 4.55,
|
| 210 |
+
"learning_rate": 2.736318407960199e-05,
|
| 211 |
+
"loss": 0.0777,
|
| 212 |
+
"step": 280
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 4.71,
|
| 216 |
+
"learning_rate": 2.653399668325042e-05,
|
| 217 |
+
"loss": 0.064,
|
| 218 |
+
"step": 290
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 4.87,
|
| 222 |
+
"learning_rate": 2.570480928689884e-05,
|
| 223 |
+
"loss": 0.0843,
|
| 224 |
+
"step": 300
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 4.99,
|
| 228 |
+
"eval_accuracy": 0.9843342036553525,
|
| 229 |
+
"eval_loss": 0.03356986492872238,
|
| 230 |
+
"eval_runtime": 4.4121,
|
| 231 |
+
"eval_samples_per_second": 86.806,
|
| 232 |
+
"eval_steps_per_second": 10.879,
|
| 233 |
+
"step": 307
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 5.03,
|
| 237 |
+
"learning_rate": 2.4875621890547266e-05,
|
| 238 |
+
"loss": 0.13,
|
| 239 |
+
"step": 310
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 5.2,
|
| 243 |
+
"learning_rate": 2.4046434494195688e-05,
|
| 244 |
+
"loss": 0.0658,
|
| 245 |
+
"step": 320
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 5.36,
|
| 249 |
+
"learning_rate": 2.3217247097844114e-05,
|
| 250 |
+
"loss": 0.0632,
|
| 251 |
+
"step": 330
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 5.52,
|
| 255 |
+
"learning_rate": 2.238805970149254e-05,
|
| 256 |
+
"loss": 0.0878,
|
| 257 |
+
"step": 340
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 5.68,
|
| 261 |
+
"learning_rate": 2.155887230514096e-05,
|
| 262 |
+
"loss": 0.0493,
|
| 263 |
+
"step": 350
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 5.85,
|
| 267 |
+
"learning_rate": 2.0729684908789386e-05,
|
| 268 |
+
"loss": 0.0744,
|
| 269 |
+
"step": 360
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 5.99,
|
| 273 |
+
"eval_accuracy": 0.9843342036553525,
|
| 274 |
+
"eval_loss": 0.039609070867300034,
|
| 275 |
+
"eval_runtime": 4.388,
|
| 276 |
+
"eval_samples_per_second": 87.284,
|
| 277 |
+
"eval_steps_per_second": 10.939,
|
| 278 |
+
"step": 369
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 6.01,
|
| 282 |
+
"learning_rate": 1.990049751243781e-05,
|
| 283 |
+
"loss": 0.0987,
|
| 284 |
+
"step": 370
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 6.17,
|
| 288 |
+
"learning_rate": 1.9071310116086237e-05,
|
| 289 |
+
"loss": 0.0885,
|
| 290 |
+
"step": 380
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 6.33,
|
| 294 |
+
"learning_rate": 1.8242122719734662e-05,
|
| 295 |
+
"loss": 0.0541,
|
| 296 |
+
"step": 390
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 6.5,
|
| 300 |
+
"learning_rate": 1.7412935323383088e-05,
|
| 301 |
+
"loss": 0.0499,
|
| 302 |
+
"step": 400
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 6.66,
|
| 306 |
+
"learning_rate": 1.658374792703151e-05,
|
| 307 |
+
"loss": 0.053,
|
| 308 |
+
"step": 410
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 6.82,
|
| 312 |
+
"learning_rate": 1.5754560530679935e-05,
|
| 313 |
+
"loss": 0.058,
|
| 314 |
+
"step": 420
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 6.98,
|
| 318 |
+
"learning_rate": 1.4925373134328357e-05,
|
| 319 |
+
"loss": 0.0702,
|
| 320 |
+
"step": 430
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 7.0,
|
| 324 |
+
"eval_accuracy": 0.97911227154047,
|
| 325 |
+
"eval_loss": 0.06899962574243546,
|
| 326 |
+
"eval_runtime": 4.5228,
|
| 327 |
+
"eval_samples_per_second": 84.682,
|
| 328 |
+
"eval_steps_per_second": 10.613,
|
| 329 |
+
"step": 431
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 7.15,
|
| 333 |
+
"learning_rate": 1.4096185737976782e-05,
|
| 334 |
+
"loss": 0.0678,
|
| 335 |
+
"step": 440
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 7.31,
|
| 339 |
+
"learning_rate": 1.326699834162521e-05,
|
| 340 |
+
"loss": 0.06,
|
| 341 |
+
"step": 450
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 7.47,
|
| 345 |
+
"learning_rate": 1.2437810945273633e-05,
|
| 346 |
+
"loss": 0.0527,
|
| 347 |
+
"step": 460
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 7.63,
|
| 351 |
+
"learning_rate": 1.1608623548922057e-05,
|
| 352 |
+
"loss": 0.0462,
|
| 353 |
+
"step": 470
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 7.8,
|
| 357 |
+
"learning_rate": 1.077943615257048e-05,
|
| 358 |
+
"loss": 0.0682,
|
| 359 |
+
"step": 480
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 7.96,
|
| 363 |
+
"learning_rate": 9.950248756218906e-06,
|
| 364 |
+
"loss": 0.063,
|
| 365 |
+
"step": 490
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 7.99,
|
| 369 |
+
"eval_accuracy": 0.9843342036553525,
|
| 370 |
+
"eval_loss": 0.03944966197013855,
|
| 371 |
+
"eval_runtime": 4.9394,
|
| 372 |
+
"eval_samples_per_second": 77.54,
|
| 373 |
+
"eval_steps_per_second": 9.718,
|
| 374 |
+
"step": 492
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 8.12,
|
| 378 |
+
"learning_rate": 9.121061359867331e-06,
|
| 379 |
+
"loss": 0.0879,
|
| 380 |
+
"step": 500
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 8.28,
|
| 384 |
+
"learning_rate": 8.291873963515755e-06,
|
| 385 |
+
"loss": 0.081,
|
| 386 |
+
"step": 510
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 8.45,
|
| 390 |
+
"learning_rate": 7.4626865671641785e-06,
|
| 391 |
+
"loss": 0.0488,
|
| 392 |
+
"step": 520
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 8.61,
|
| 396 |
+
"learning_rate": 6.633499170812605e-06,
|
| 397 |
+
"loss": 0.0692,
|
| 398 |
+
"step": 530
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 8.77,
|
| 402 |
+
"learning_rate": 5.804311774461028e-06,
|
| 403 |
+
"loss": 0.0384,
|
| 404 |
+
"step": 540
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 8.93,
|
| 408 |
+
"learning_rate": 4.975124378109453e-06,
|
| 409 |
+
"loss": 0.0497,
|
| 410 |
+
"step": 550
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 9.0,
|
| 414 |
+
"eval_accuracy": 0.9869451697127938,
|
| 415 |
+
"eval_loss": 0.03008684515953064,
|
| 416 |
+
"eval_runtime": 4.4989,
|
| 417 |
+
"eval_samples_per_second": 85.132,
|
| 418 |
+
"eval_steps_per_second": 10.669,
|
| 419 |
+
"step": 554
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 9.1,
|
| 423 |
+
"learning_rate": 4.145936981757877e-06,
|
| 424 |
+
"loss": 0.0456,
|
| 425 |
+
"step": 560
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 9.26,
|
| 429 |
+
"learning_rate": 3.3167495854063024e-06,
|
| 430 |
+
"loss": 0.0874,
|
| 431 |
+
"step": 570
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 9.42,
|
| 435 |
+
"learning_rate": 2.4875621890547264e-06,
|
| 436 |
+
"loss": 0.0569,
|
| 437 |
+
"step": 580
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 9.58,
|
| 441 |
+
"learning_rate": 1.6583747927031512e-06,
|
| 442 |
+
"loss": 0.0613,
|
| 443 |
+
"step": 590
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 9.74,
|
| 447 |
+
"learning_rate": 8.291873963515756e-07,
|
| 448 |
+
"loss": 0.0389,
|
| 449 |
+
"step": 600
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 9.91,
|
| 453 |
+
"learning_rate": 0.0,
|
| 454 |
+
"loss": 0.0502,
|
| 455 |
+
"step": 610
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 9.91,
|
| 459 |
+
"eval_accuracy": 0.9895561357702349,
|
| 460 |
+
"eval_loss": 0.029892772436141968,
|
| 461 |
+
"eval_runtime": 5.862,
|
| 462 |
+
"eval_samples_per_second": 65.336,
|
| 463 |
+
"eval_steps_per_second": 8.188,
|
| 464 |
+
"step": 610
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 9.91,
|
| 468 |
+
"step": 610,
|
| 469 |
+
"total_flos": 8.479620642524774e+17,
|
| 470 |
+
"train_loss": 0.11231542806156346,
|
| 471 |
+
"train_runtime": 1101.7928,
|
| 472 |
+
"train_samples_per_second": 31.249,
|
| 473 |
+
"train_steps_per_second": 0.554
|
| 474 |
}
|
| 475 |
],
|
| 476 |
+
"max_steps": 610,
|
| 477 |
+
"num_train_epochs": 10,
|
| 478 |
+
"total_flos": 8.479620642524774e+17,
|
| 479 |
"trial_name": null,
|
| 480 |
"trial_params": null
|
| 481 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3643
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:33f2895d6c5050e456be1d25e128ea3fe239bcccdc3e3fc8b645391a78acaba4
|
| 3 |
size 3643
|